Metraipolis › archive › dc_3ca424c25b03
Avatar: Toward Autonomous End-to-End Orchestration of Scientific Workflows using LLMs — arXiv:2609.10509
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.10509
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T07:23:56.264Z
- SHA-256 of the archived text
b72ea46c724841e987e5ac220c899146b2eeb36c0e8b27911a49fc695c57bf5d- Stable URL of this page
https://metraipolis.com/documento/dc_3ca424c25b03
How to cite
Avatar: Toward Autonomous End-to-End Orchestration of Scientific Workflows using LLMs — arXiv:2609.10509 — arXiv (en), https://arxiv.org/abs/2609.10509 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3ca424c25b03 (Metraipolis archive dc_3ca424c25b03, sha256 b72ea46c724841e987e5ac220c899146b2eeb36c0e8b27911a49fc695c57bf5d)
BibTeX
@misc{dc3ca424c25b03,
title = {Avatar: Toward Autonomous End-to-End Orchestration of Scientific Workflows using LLMs — arXiv:2609.10509},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.10509},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3ca424c25b03; sha256 b72ea46c724841e987e5ac220c899146b2eeb36c0e8b27911a49fc695c57bf5d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10509. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Scientific workflow management (WMSs) systems automate execution, yet orchestrate using fixed, hand-tuned rules. LLM agents promise more autonomous orchestration, but it remains unclear where to introduce agentic reasoning, how to bound its risk, and when it actually helps. We present Avatar, an actor-based architecture comprising an orchestrator, an executor, and a provenance monitor. Each actor's decision policy is pluggable (rule-based or LLM-backed) via a single adapter-validated action catalog, so conventional and agentic control run on the same core across different WMSs. We present an implementation using the Academy framework and evaluate Avatar across three workloads. We observe that Avatar's rule mode reproduces native execution, with a single unchanged core running all three. Moreover, LLM-backed Avatar reports a reduction of compute wastage by $55\%$ and cuts GPU-busy time by $40\%$. Overall, we envision Avatar as a step toward workflow systems that reason about their own orchestration rather than follow pre-fixed rules. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.MA). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.10509 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T06:59:55.771Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).